Triple
T38584779
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shadow Labyrinth |
E932321
|
entity |
| Predicate | keyObtainedFrom |
P191226
|
FINISHED |
| Object | Lower City reputation quest chain |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Lower City reputation quest chain | Statement: [Shadow Labyrinth, keyObtainedFrom, Lower City reputation quest chain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyObtainedFrom Context triple: [Shadow Labyrinth, keyObtainedFrom, Lower City reputation quest chain]
-
A.
keyUse
Indicates that one entity is used as a key or means of access, control, or identification for another entity.
-
B.
keyClient
Indicates that one entity is a primary or strategically important client of another entity.
-
C.
keyOutput
Indicates that an entity functions as a primary or essential result, product, or outcome produced by another entity or process.
-
D.
keyCenter
Indicates the central or primary tonal focus around which other related elements are organized or interpreted.
-
E.
keyMaterial
Indicates that an entity serves as cryptographic key material used to secure, encrypt, or authenticate data in a security-related relationship.
- F. None of above. chosen
Provenance (4 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdaa36f90819093f8661969990c7d |
completed | May 7, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fefc588190b063d7ea1ec87b07 |
completed | May 7, 2026, 6:25 p.m. |
| PDg | Predicate description generation | batch_69fcdaa2bfc08190beccabb0f1782d0d |
completed | May 7, 2026, 6:32 p.m. |
Created at: May 3, 2026, 4:32 p.m.